Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling
By: Ivan Rodkin , Daniil Orel , Konstantin Smirnov and more
Potential Business Impact:
Makes computers better at thinking through problems.
Reasoning is a core capability of large language models, yet understanding how they learn and perform multi-step reasoning remains an open problem. In this study, we explore how different architectures and training methods affect model multi-step reasoning capabilities within a cellular automata framework. By training on state sequences generated with random Boolean functions for random initial conditions to exclude memorization, we demonstrate that most neural architectures learn to abstract the underlying rules. While models achieve high accuracy in next-state prediction, their performance declines sharply if multi-step reasoning is required. We confirm that increasing model depth plays a crucial role for sequential computations. We demonstrate that an extension of the effective model depth with recurrence, memory, and test-time compute scaling substantially enhances reasoning capabilities.
Similar Papers
RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
Artificial Intelligence
Helps computers solve hard problems by learning steps.
Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning
Machine Learning (CS)
Makes AI think faster and use less power.
MixReasoning: Switching Modes to Think
Artificial Intelligence
Smart AI learns faster by skipping easy steps.